Forecasting USD/CNY Exchange Rates Using Machine Learning
DOI:
https://doi.org/10.62051/ve4mrv31Keywords:
Exchange rate forecasting; USD/CNY; Time series prediction; Deep learning; Financial modeling.Abstract
Exchange rate prediction is important in global trade, investment, and financial decision-making. The USD/CNY exchange rate in particular has received much attention due to China’s growing role in the global economy. However, predicting exchange rates is difficult because the data is complex, nonlinear, and often influenced by many factors. This research focuses on predicting the USD/CNY exchange rate using machine learning-based approaches. Three models are evaluated and compared in this work: SVR, LSTM, and GRU. Historical exchange rate data is from January 1, 2015, to March 20, 2025. Model performance is evaluated by the R²score, MSE, MAE, and RMSE. The results show that all three models can capture exchange rate trends. GRU achieves the highest performance. It reaches an R²score of 0.9311 and the lowest error metric. LSTM reaches an R² of 0.9141.SVR reaches an R² of 0.9005 The findings suggest that deep learning approaches offer better results in financial time series forecasting and it can provide valuable insights for future applications in exchange rate prediction.
Downloads
References
[1] Shumway R H, Stoffer D S. ARIMA models. Time Series Analysis and Its Applications: With R Examples, 2017: 75–163.
[2] Bauwens L, Laurent S, Rombouts J V K. Multivariate GARCH models: a survey. Journal of Applied Econometrics, 2006, 21(1): 79–109.
[3] Tay F E H, Shen L. Economic and financial prediction using rough sets model. European Journal of Operational Research, 2002, 141(3): 641–659.
[4] Basak D, Pal S, Patranabis D C. Support vector regression. Neural Information Processing-Letters and Reviews, 2007, 11(10): 203–224.
[5] Gers F A, Schmidhuber J, Cummins F. Learning to forget: Continual prediction with LSTM. Neural Computation, 2000, 12(10): 2451–2471.
[6] Sola J, Sevilla J. Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE Transactions on Nuclear Science, 1997, 44(3): 1464–1468.
[7] Awad M, Khanna R. Support vector regression. Efficient Learning Machines: Theories, Concepts, and Applications for Engineers and System Designers, 2015: 67–80.
[8] Sherstinsky A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phenomena, 2020, 404: 132306.
[9] Siami-Namini S, Tavakoli N, Namin A S. The performance of LSTM and BiLSTM in forecasting time series. IEEE International Conference on Big Data (Big Data), 2019: 3285–3292.
[10] Dey R, Salem F M. Gate-variants of gated recurrent unit (GRU) neural networks. IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS), 2017: 1597–1600.
[11] Fu R, Zhang Z, Li L. Using LSTM and GRU neural network methods for traffic flow prediction. 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC), 2016: 324–328.
Downloads
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2025 Transactions on Computer Science and Intelligent Systems Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
